A dynamic generalization of the Rasch model (Q1309411)

The paper presents a mathematical learning model which is a combination of the Rasch model and the concept of incomplete data with the use of so- called ``virtual items''. After formulation of a very general model the authors study extensively the subclass of models with commuting operators. It turns out that the model presented is a generalization of a class of models known as Luce's bet models. The paper includes estimation procedures, examples and exhaustive references.